# Efficient Multiuser AI Downloading via Reusable Knowledge Broadcasting arXiv: https://arxiv.org/abs/2307.15316 ยท HTML: https://mlsanity.com/paper/2307.15316/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 25 of its 41 references that are in the map. - First posted on arXiv 28 Jul 2023. ## Builds on (most cited first, 25 of 25) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014) - [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021) - [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019) - [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019) - [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019) - [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021) - [Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation](https://mlsanity.com/paper/1903.10992/) (2019) - [Neuron Shapley: Discovering the Responsible Neurons](https://mlsanity.com/paper/2002.09815/) (2020) - [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021) - [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019) - [Wireless Network Intelligence at the Edge](https://mlsanity.com/paper/1812.02858/) (2018) - [Deep Model Reassembly](https://mlsanity.com/paper/2210.17409/) (2022) - [Communication-Computation Trade-Off in Resource-Constrained Edge Inference](https://mlsanity.com/paper/2006.02166/) (2020) - [Task-Oriented Communication for Multi-Device Cooperative Edge Inference](https://mlsanity.com/paper/2109.00172/) (2021) - [DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2206.08100/) (2022) - [Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI](https://mlsanity.com/paper/2207.00969/) (2022) - [Stitchable Neural Networks](https://mlsanity.com/paper/2302.06586/) (2023) - [Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning](https://mlsanity.com/paper/1903.03472/) (2019) - [Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)](https://mlsanity.com/paper/2204.05223/) (2022) - [Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference](https://mlsanity.com/paper/2105.13618/) (2021) - [An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems](https://mlsanity.com/paper/2205.12755/) (2022) - [Compression and Acceleration of Neural Networks for Communications](https://mlsanity.com/paper/1907.13269/) (2019) - [In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks](https://mlsanity.com/paper/2210.03555/) (2022) ## Built on by (most cited first, 5 of 5) - [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024) - [TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks](https://mlsanity.com/paper/2405.03990/) (2024) - [Resource Management for Low-latency Cooperative Fine-tuning of Foundation Models at the Network Edge](https://mlsanity.com/paper/2407.09873/) (2024) - [Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edge](https://mlsanity.com/paper/2503.13421/) (2025) - [Fine-Grained AI Model Caching and Downloading With Coordinated Multipoint Broadcasting in Multi-Cell Edge Networks](https://mlsanity.com/paper/2509.19341/) (2025) ## Abstract (arXiv) For the 6G mobile networks, in-situ model downloading has emerged as an important use case to enable real-time adaptive artificial intelligence on edge devices. However, the simultaneous downloading of diverse and high-dimensional models to multiple devices over wireless links presents a significant communication bottleneck. To overcome the bottleneck, we propose the framework of model broadcasting and assembling (MBA), which represents the first attempt on leveraging reusable knowledge, referring to shared parameters among tasks, to enable parameter broadcasting to reduce communication overhead. The MBA framework comprises two key components. The first, the MBA protocol, defines the system operations including parameter selection from a model library, power control for broadcasting, and model assembling at devices. The second component is the joint design of parameter-selection-and-power-control (PS-PC), which provides guarantees on devices' model performance and minimizes the downloading latency. The corresponding optimization problem is simplified by decomposition into the sequential PS and PC sub-problems without compromising its optimality. The PS sub-problem is solved efficiently by designing two efficient algorithms. On one hand, the low-complexity algorithm of greedy parameter selection features the construction of candidate model sets and a selection metric, both of which are designed under the criterion of maximum reusable knowledge among tasks. On the other hand, the optimal tree-search algorithm gains its efficiency via the proposed construction of a compact binary tree pruned using model architecture constraints and an intelligent branch-and-bound search. Given optimal PS, the optimal PC policy is derived in closed form. Extensive experiments demonstrate the substantial reduction in downloading latency achieved by the proposed MBA compared to traditional model downloading.